unpublish-product

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden and it does disclose post-condition state ("returns the product's state on every channel afterwards") and the presence of `userErrors` — useful mutation context. However, it never covers the important edge cases: whether unpublishing a channel the product isn't published to is an error or a no-op, whether partial failure leaves some channels unpublished, or what permissions are required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: operation and channel targeting first, return shape second. Every clause carries information and nothing is padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description compensates for the missing output schema by sketching the return (per-channel state + userErrors), which is genuinely helpful for a mutation tool. But with zero annotations and no output schema, the definition should also cover destructive scope (removes the listing from live channels) and error/partial-success behavior; those gaps leave it only adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baselines apply and the schema already documents productId GID format and the OR-constraint between publicationIds and publicationNames. The description echoes the alternative and stresses "exact" names, but adds no new format or resolution semantics beyond what the schema fields state.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ("Unpublish a product") with explicit scope ("from one or more sales channels"), which unambiguously marks it as the inverse of the publish-product sibling. An agent needs no further reading to know what it does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives the prerequisite lookup step ("see get-publications") and names the two mutually exclusive ways to identify channels, which is exactly the decision the caller must make. It does not spell out when to prefer IDs over names (IDs are authoritative, names are convenience) or note when this tool should not be used, so it falls short of explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.